用requests库和lxml库，爬取PPT图像素材。

import requests
import os
from lxml import etree
from requests.exceptions import RequestException

url_list = []
base_url = 'http://online.sccnn.com/html/cion/index-'
# 存放文件的地址
pach = './ico/'
# 爬取的最大页数
max_page = 20
# 爬取的起始页数
start_page = 1


def get_page(url):
    """
    获取url的HTML信息
    :param url:传入一个主页url
    :return: 返回一个二进制的字符串，用于XPATH解析
    """
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3)'
                      ' AppleWebKit/537.36 (KHTML, like Gecko)'
                      ' Chrome/65.0.3325.162 Safari/537.36'
    }
    try:
        html = requests.get(url, headers=headers)
        print('正在解析当前页面的信息……')
        if html.status_code == 200:
            return html.content
        return None

    except RequestException:
        return None


def parse_html(content):
    """

    :param content: 接受一个二进制的原生字符串，用于解析
    :return: 返回一个分页的url列表
    """
    result_list = []
    html = etree.HTML(content)
    result = html.xpath('//table//table//table//td//a/@href')
    print("正在获取页面内各个图片集的链接……")
    for i in result:
        if 'http://online.sccnn.com/html/cion/png' in i and not i in result_list:
            result_list.append(i)
        else:
            continue
    return result_list


def make_dir(file_path):
    """
    如果文件夹不存在，就创造一个文件夹
    :param file_path: 传入一个文件夹的路径
    """
    if not os.path.exists(file_path):
        os.makedirs(file_path)
        print("【%s】文件夹不存在，正在创建！" % file_path)


def get_ico(url_list):
    """
    访问子页面的url，并获取图标的链接与名称。并且在保持路径下，名称文件夹内，保持图片文件。
    :param url_list: 子页面的url
    :return:
    """
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3)'
                      ' AppleWebKit/537.36 (KHTML, like Gecko)'
                      ' Chrome/65.0.3325.162 Safari/537.36'
    }

    for url in url_list:
        try:
            html = requests.get(url, headers=headers)
            if html.status_code == 200:
                index_num = 0
                href = etree.HTML(html.content)
                main_name = href.xpath('//td[@style="WORD-BREAK: break-all"]/text()')
                print('正在爬取【%s】目录下的图标' % main_name[0])
                ico_src = href.xpath('//img[@title="点击查看原图"]/@src')
                # 这里加一个判断，是因为html信息中，有部分空文件夹里面没有内容
                if len(ico_src) > 3:
                    make_dir(pach + main_name[0])
                for li in ico_src:
                    print('正在爬取%s第%d张' % (main_name, index_num + 1))
                    index_num += 1
                    get_jpg = requests.get('http://online.sccnn.com/' + li[8:])
                    with open(pach + main_name[0] + '/' + str(index_num) + '.png', 'wb') as f:
                        f.write(get_jpg.content)
        except RequestException:
            return None


if __name__ == '__main__':
    for num in range(start_page, max_page):
        print('正在爬取第%s页的图标……' % num)
        home_page = get_page(base_url + str(num) + '.htm')
        url_list = parse_html(home_page)
        get_ico(url_list)